Applying Spiking Neural Nets to Noise Shaping

TL;DR

This paper explores how the weights in spiking neural networks influence noise shaping properties, introduces a post-processing method to align their output with Delta-Sigma Modulators, and discusses industrial applications in oversampled A/D converters.

Contribution

It systematically analyzes the effect of network weights on noise shaping and proposes a post-processing technique to improve output signal quality in spiking neural networks.

Findings

Network weights significantly affect noise shaping properties.

A new post-processing method improves output signal alignment with Delta-Sigma Modulators.

Potential for industrial application in oversampled A/D converters.

Abstract

-In recent years, there has been an increased focus on the mechanics of information transmission in spiking neural networks. Especially the Noise Shaping properties of these networks and their similarity to Delta-Sigma Modulators has received a lot of attention. However, very little of the research done in this area has focused on the effect the weights in these networks have on the Noise Shaping properties and on post- processing of the network output signal. This paper concerns itself with the various modes of network operation and beneficial as well as detrimental effects which the systematic generation of network weights can effect. Also, a method for post-processing of the spiking output signal is introduced, bringing the output signal more in line with conventional Delta-Sigma Modulators. Relevancy of this research to industrial application of neural nets as building blocks of oversampled A/D converters is shown. Also, further points of contention are listed, which must be thoroughly researched to add to the above mentioned applicability of spiking neural nets.